accelerate/pr_4021/en/usage_guides/big_modeling.html

<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Big Model Inference&quot;,&quot;local&quot;:&quot;big-model-inference&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Accelerate&quot;,&quot;local&quot;:&quot;accelerate&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Hugging Face ecosystem&quot;,&quot;local&quot;:&quot;hugging-face-ecosystem&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Next steps&quot;,&quot;local&quot;:&quot;next-steps&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}">
		<link href="/docs/accelerate/pr_4021/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
		<link rel="modulepreload" href="/docs/accelerate/pr_4021/en/_app/immutable/entry/start.8a49e72b.js">
		<link rel="modulepreload" href="/docs/accelerate/pr_4021/en/_app/immutable/chunks/scheduler.b9285784.js">
		<link rel="modulepreload" href="/docs/accelerate/pr_4021/en/_app/immutable/chunks/singletons.7547c222.js">
		<link rel="modulepreload" href="/docs/accelerate/pr_4021/en/_app/immutable/chunks/index.6d423e5c.js">
		<link rel="modulepreload" href="/docs/accelerate/pr_4021/en/_app/immutable/chunks/paths.d42c9205.js">
		<link rel="modulepreload" href="/docs/accelerate/pr_4021/en/_app/immutable/entry/app.1df4d18e.js">
		<link rel="modulepreload" href="/docs/accelerate/pr_4021/en/_app/immutable/chunks/preload-helper.b0bd19d1.js">
		<link rel="modulepreload" href="/docs/accelerate/pr_4021/en/_app/immutable/chunks/index.26bc89a1.js">
		<link rel="modulepreload" href="/docs/accelerate/pr_4021/en/_app/immutable/nodes/0.0e7c56e8.js">
		<link rel="modulepreload" href="/docs/accelerate/pr_4021/en/_app/immutable/chunks/each.e59479a4.js">
		<link rel="modulepreload" href="/docs/accelerate/pr_4021/en/_app/immutable/nodes/38.925675f7.js">
		<link rel="modulepreload" href="/docs/accelerate/pr_4021/en/_app/immutable/chunks/MermaidChart.svelte_svelte_type_style_lang.7a0ae628.js">
		<link rel="modulepreload" href="/docs/accelerate/pr_4021/en/_app/immutable/chunks/Youtube.fd47a3ef.js">
		<link rel="modulepreload" href="/docs/accelerate/pr_4021/en/_app/immutable/chunks/CodeBlock.844ff9c3.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Big Model Inference&quot;,&quot;local&quot;:&quot;big-model-inference&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Accelerate&quot;,&quot;local&quot;:&quot;accelerate&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Hugging Face ecosystem&quot;,&quot;local&quot;:&quot;hugging-face-ecosystem&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Next steps&quot;,&quot;local&quot;:&quot;next-steps&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}"><!-- HEAD_svelte-u9bgzb_END -->      <p></p>   <div class="items-center shrink-0 min-w-[100px] max-sm:min-w-[50px] justify-end ml-auto flex" style="float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"><div class="inline-flex rounded-md max-sm:rounded-sm"><button class="inline-flex items-center gap-1 h-7 max-sm:h-7 px-2 max-sm:px-1.5 text-sm font-medium text-gray-800 border border-r-0 rounded-l-md max-sm:rounded-l-sm border-gray-200 bg-white hover:shadow-inner dark:border-gray-850 dark:bg-gray-950 dark:text-gray-200 dark:hover:bg-gray-800" aria-live="polite"><span class="inline-flex items-center justify-center rounded-md p-0.5 max-sm:p-0 hover:text-gray-800 dark:hover:text-gray-200"><svg class="sm:size-3.5 size-3" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg></span> <span>Copy page</span></button> <button class="inline-flex items-center justify-center w-6 max-sm:w-5 h-7 max-sm:h-7 disabled:pointer-events-none text-sm text-gray-500 hover:text-gray-700 dark:hover:text-white rounded-r-md max-sm:rounded-r-sm border border-l transition border-gray-200 bg-white hover:shadow-inner dark:border-gray-850 dark:bg-gray-950 dark:text-gray-200 dark:hover:bg-gray-800" aria-haspopup="menu" aria-expanded="false" aria-label="Open copy menu"><svg class="transition-transform text-gray-400 overflow-visible sm:size-3.5 size-3 rotate-0" width="1em" height="1em" viewBox="0 0 12 7" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M1 1L6 6L11 1" stroke="currentColor"></path></svg></button></div> </div>  <h1 class="relative group"><a id="big-model-inference" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#big-model-inference"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Big Model Inference</span></h1> <p data-svelte-h="svelte-1njjewm">One of the biggest advancements Accelerate provides is <a href="../concept_guides/big_model_inference">Big Model Inference</a>, which allows you to perform inference with models that don’t fully fit on your graphics card.</p> <p data-svelte-h="svelte-1hrff2w">This tutorial will show you how to use Big Model Inference in Accelerate and the Hugging Face ecosystem.</p>  <h2 class="relative group"><a id="accelerate" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#accelerate"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Accelerate</span></h2> <p data-svelte-h="svelte-w5qfqd">A typical workflow for loading a PyTorch model is shown below. <code>ModelClass</code> is a model that exceeds the GPU memory of your device (mps or cuda or xpu).</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> torch

my_model = ModelClass(...)
state_dict = torch.load(checkpoint_file)
my_model.load_state_dict(state_dict)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-91fu20">With Big Model Inference, the first step is to init an empty skeleton of the model with the <code>init_empty_weights</code> context manager. This doesn’t require any memory because <code>my_model</code> is “parameterless”.</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">from</span> accelerate <span class="hljs-keyword">import</span> init_empty_weights
<span class="hljs-keyword">with</span> init_empty_weights():
    my_model = ModelClass(...)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-158zzkm">Next, the weights are loaded into the model for inference.</p> <p data-svelte-h="svelte-1amcb59">The <a href="/docs/accelerate/pr_4021/en/package_reference/big_modeling#accelerate.load_checkpoint_and_dispatch">load_checkpoint_and_dispatch()</a> method loads a checkpoint inside your empty model and dispatches the weights for each layer across all available devices, starting with the fastest devices (GPU, MPS, XPU, NPU, MLU, SDAA, MUSA) first before moving to the slower ones (CPU and hard drive).</p> <p data-svelte-h="svelte-6ilppp">Setting <code>device_map=&quot;auto&quot;</code> automatically fills all available space on the GPU(s) first, then the CPU, and finally, the hard drive (the absolute slowest option) if there is still not enough memory.</p> <blockquote class="tip" data-svelte-h="svelte-1s1ycch"><p>Refer to the <a href="../concept_guides/big_model_inference#designing-a-device-map">Designing a device map</a> guide for more details on how to design your own device map.</p></blockquote> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">from</span> accelerate <span class="hljs-keyword">import</span> load_checkpoint_and_dispatch

model = load_checkpoint_and_dispatch(
    model, checkpoint=checkpoint_file, device_map=<span class="hljs-string">&quot;auto&quot;</span>
)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-iajmu4">If there are certain “chunks” of layers that shouldn’t be split, pass them to <code>no_split_module_classes</code> (see <a href="../concept_guides/big_model_inference#loading-weights">here</a> for more details).</p> <p data-svelte-h="svelte-lf7k2g">A models weights can also be sharded into multiple checkpoints to save memory, such as when the <code>state_dict</code> doesn’t fit in memory (see <a href="../concept_guides/big_model_inference#sharded-checkpoints">here</a> for more details).</p> <p data-svelte-h="svelte-7amkht">Now that the model is fully dispatched, you can perform inference.</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-built_in">input</span> = torch.randn(<span class="hljs-number">2</span>,<span class="hljs-number">3</span>)
device_type = <span class="hljs-built_in">next</span>(<span class="hljs-built_in">iter</span>(model.parameters())).device.<span class="hljs-built_in">type</span>
<span class="hljs-built_in">input</span> = <span class="hljs-built_in">input</span>.to(device_type)
output = model(<span class="hljs-built_in">input</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-3b5yt7">Each time an input is passed through a layer, it is sent from the CPU to the GPU (or disk to CPU to GPU), the output is calculated, and the layer is removed from the GPU going back down the line. While this adds some overhead to inference, it enables you to run any size model on your system, as long as the largest layer fits on your GPU.</p> <p data-svelte-h="svelte-1y01w5b">Multiple GPUs, or “model parallelism”, can be utilized but only one GPU will be active at any given moment. This forces the GPU to wait for the previous GPU to send it the output. You should launch your script normally with Python instead of other tools like torchrun and accelerate launch.</p> <blockquote class="tip" data-svelte-h="svelte-lzl68u"><p>You may also be interested in <em>pipeline parallelism</em> which utilizes all available GPUs at once, instead of only having one GPU active at a time. This approach is less flexible though. For more details, refer to the <a href="./distributed_inference#memory-efficient-pipeline-parallelism-experimental">Memory-efficient pipeline parallelism</a> guide.</p></blockquote> <iframe class="w-full xl:w-4/6 h-80" src="https://www.youtube-nocookie.com/embed/MWCSGj9jEAo" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe> <p data-svelte-h="svelte-1yv5ji4">Take a look at a full example of Big Model Inference below.</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> torch
<span class="hljs-keyword">from</span> accelerate <span class="hljs-keyword">import</span> init_empty_weights, load_checkpoint_and_dispatch

<span class="hljs-keyword">with</span> init_empty_weights():
    model = MyModel(...)

model = load_checkpoint_and_dispatch(
    model, checkpoint=checkpoint_file, device_map=<span class="hljs-string">&quot;auto&quot;</span>
)

<span class="hljs-built_in">input</span> = torch.randn(<span class="hljs-number">2</span>,<span class="hljs-number">3</span>)
device_type = <span class="hljs-built_in">next</span>(<span class="hljs-built_in">iter</span>(model.parameters())).device.<span class="hljs-built_in">type</span>
<span class="hljs-built_in">input</span> = <span class="hljs-built_in">input</span>.to(device_type)
output = model(<span class="hljs-built_in">input</span>)<!-- HTML_TAG_END --></pre></div>  <h2 class="relative group"><a id="hugging-face-ecosystem" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#hugging-face-ecosystem"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Hugging Face ecosystem</span></h2> <p data-svelte-h="svelte-1sxxcso">Other libraries in the Hugging Face ecosystem, like Transformers or Diffusers, supports Big Model Inference in their <a href="https://huggingface.co/docs/transformers/main/en/main_classes/model#transformers.PreTrainedModel.from_pretrained" rel="nofollow">from_pretrained</a> constructors.</p> <p data-svelte-h="svelte-owwo1o">You just need to add <code>device_map=&quot;auto&quot;</code> in <a href="https://huggingface.co/docs/transformers/main/en/main_classes/model#transformers.PreTrainedModel.from_pretrained" rel="nofollow">from_pretrained</a> to enable Big Model Inference.</p> <p data-svelte-h="svelte-ois3cz">For example, load Big Sciences T0pp 11 billion parameter model with Big Model Inference.</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoModelForSeq2SeqLM

model = AutoModelForSeq2SeqLM.from_pretrained(<span class="hljs-string">&quot;bigscience/T0pp&quot;</span>, device_map=<span class="hljs-string">&quot;auto&quot;</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-25ai00">After loading the model, the empty init and smart dispatch steps from before are executed and the model is fully ready to make use of all the resources in your machine. Through these constructors, you can also save more memory by specifying the <code>torch_dtype</code> parameter to load a model in a lower precision.</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600 " title="code excerpt" type="button"><svg class="" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg> <div class="absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0"><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent; "></div> Copied</div></button></div> <pre class=""><!-- HTML_TAG_START --><span class="hljs-keyword">from</span> transformers <span class="hljs-keyword">import</span> AutoModelForSeq2SeqLM

model = AutoModelForSeq2SeqLM.from_pretrained(<span class="hljs-string">&quot;bigscience/T0pp&quot;</span>, device_map=<span class="hljs-string">&quot;auto&quot;</span>, torch_dtype=torch.float16)<!-- HTML_TAG_END --></pre></div>  <h2 class="relative group"><a id="next-steps" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#next-steps"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Next steps</span></h2> <p data-svelte-h="svelte-2pv49y">For a more detailed explanation of Big Model Inference, make sure to check out the <a href="../concept_guides/big_model_inference">conceptual guide</a>!</p> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/accelerate/blob/main/docs/source/usage_guides/big_modeling.md" target="_blank"><svg class="mr-1" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M31,16l-7,7l-1.41-1.41L28.17,16l-5.58-5.59L24,9l7,7z"></path><path d="M1,16l7-7l1.41,1.41L3.83,16l5.58,5.59L8,23l-7-7z"></path><path d="M12.419,25.484L17.639,6.552l1.932,0.518L14.351,26.002z"></path></svg> <span data-svelte-h="svelte-zjs2n5"><span class="underline">Update</span> on GitHub</span></a>  <p></p> 
			
			<script>
				{
					__sveltekit_1q7nz6m = {
						assets: "/docs/accelerate/pr_4021/en",
						base: "/docs/accelerate/pr_4021/en",
						env: {}
					};

					const element = document.currentScript.parentElement;

					const data = [null,null];

					Promise.all([
						import("/docs/accelerate/pr_4021/en/_app/immutable/entry/start.8a49e72b.js"),
						import("/docs/accelerate/pr_4021/en/_app/immutable/entry/app.1df4d18e.js")
					]).then(([kit, app]) => {
						kit.start(app, element, {
							node_ids: [0, 38],
							data,
							form: null,
							error: null
						});
					});
				}
			</script>